HealthMamba: An Uncertainty-aware Spatiotemporal Graph State Space Model for Effective and Reliable Healthcare Facility Visit Prediction

Researchers have developed HealthMamba, a new AI framework that uses spatiotemporal modeling and uncertainty quantification to predict healthcare facility visits more accurately. The system achieved 6% better prediction accuracy and 3.5% improvement in uncertainty quantification compared to existing methods when tested on real-world datasets from four US states.

• →HealthMamba introduces a novel Graph State Space Model called GraphMamba for hierarchical spatiotemporal modeling of healthcare visits.
• →The framework integrates three uncertainty quantification mechanisms to provide reliable predictions during abnormal situations like public emergencies.
• →Testing on large-scale datasets from California, New York, Texas, and Florida showed significant performance improvements over existing baselines.
• →The system addresses limitations in current approaches by considering spatial dependencies between different types of healthcare facilities.
• →The framework could optimize healthcare resource allocation and inform public health policy decisions.